Papers by Rajesh Sharma
Revisiting the Classics: A Study on Identifying and Rectifying Gender Stereotypes in Rhymes and Poems (2024.lrec-main)
Copied to clipboard
| Challenge: | This study highlights the pervasive existence of gender stereotypes in literary works and proposes a model with 97% accuracy to identify gender bias. |
| Approach: | They propose a large language model with 97% accuracy to identify gender bias in rhymes and poems and a model with a comparative survey against human educator rectifications. |
| Outcome: | The proposed model has 97% accuracy and can be used to identify gender biases in rhymes and poems. |
Investigating Prosodic Signatures via Speech Pre-Trained Models for Audio Deepfake Source Attribution (2025.findings-acl)
Copied to clipboard
| Challenge: | x-vector (speaker recognition PTM) achieves the highest performance in prosodic tasks . despite its low parameter, x vector captures unique prosodic characteristics of the sources . |
| Approach: | They propose to use SOTA speech pre-trained models to capture prosodic sig-natures of generative sources for audio deepfake source attribution. |
| Outcome: | The proposed model captures prosodic sig-natures of generative sources better than other models on ASVSpoof and CFAD. |
Heterogeneity over Homogeneity: Investigating Multilingual Speech Pre-Trained Models for Detecting Audio Deepfake (2024.findings-naacl)
Copied to clipboard
| Challenge: | a recent study has focused on audio deepfake detection (ADD) due to its ability to impersonate and share false, often malicious information. |
| Approach: | They propose to use multilingual speech Pre-Trained models for Audio deepfake detection (ADD) they propose to combine models with existing models to achieve better ADD detection . |
| Outcome: | The proposed models gain knowledge about diverse pitches, accents, and tones, during theirpre-training phase and are more robust to variations. |
That is Unacceptable: the Moral Foundations of Canceling (2025.acl-long)
Copied to clipboard
| Challenge: | Annotators' canceling attitudes are influenced by the type of controversial events and involved celebrities. |
| Approach: | They propose to annotate canceling incidents from YouTube and an annotated corpus of videos that are based on their morality to determine their canceling attitudes. |
| Outcome: | The dataset analyzes canceling attitudes of annotators from six videos and comments gathered from YouTube. |